LOOPS Generic Information Set
draft-welzl-loops-gen-info-00
The information below is for an old version of the document.
| Document | Type | Active Internet-Draft (individual) | |
|---|---|---|---|
| Authors | Michael Welzl , Carsten Bormann | ||
| Last updated | 2019-05-27 | ||
| Stream | (None) | ||
| Formats | plain text htmlized pdfized bibtex | ||
| Stream | Stream state | (No stream defined) | |
| Consensus boilerplate | Unknown | ||
| RFC Editor Note | (None) | ||
| IESG | IESG state | I-D Exists | |
| Telechat date | (None) | ||
| Responsible AD | (None) | ||
| Send notices to | (None) |
draft-welzl-loops-gen-info-00
TSVWG M. Welzl
Internet-Draft University of Oslo
Intended status: Standards Track C. Bormann, Ed.
Expires: November 28, 2019 Universitaet Bremen TZI
May 27, 2019
LOOPS Generic Information Set
draft-welzl-loops-gen-info-00
Abstract
LOOPS (Local Optimizations on Path Segments) aims to provide local
(not end-to-end but in-network) recovery of lost packets to achieve
better data delivery in the presence of losses.
[I-D.li-tsvwg-loops-problem-opportunities] provides an overview over
the problems and optimization opportunities that LOOPS could address.
The present document is a strawman for the set of information that
would be interchanged in a LOOPS protocol, without already defining a
specific data packet format.
The generic information set needs to be mapped to a specific
encapsulation protocol to actually run the LOOPS optimizations. The
current version of this document contains sketches of bindings to GUE
[I-D.ietf-intarea-gue] and Geneve [I-D.ietf-nvo3-geneve].
Status of This Memo
This Internet-Draft is submitted in full conformance with the
provisions of BCP 78 and BCP 79.
Internet-Drafts are working documents of the Internet Engineering
Task Force (IETF). Note that other groups may also distribute
working documents as Internet-Drafts. The list of current Internet-
Drafts is at https://datatracker.ietf.org/drafts/current/.
Internet-Drafts are draft documents valid for a maximum of six months
and may be updated, replaced, or obsoleted by other documents at any
time. It is inappropriate to use Internet-Drafts as reference
material or to cite them other than as "work in progress."
This Internet-Draft will expire on November 28, 2019.
Welzl & Bormann Expires November 28, 2019 [Page 1]
Internet-Draft LOOPS May 2019
Copyright Notice
Copyright (c) 2019 IETF Trust and the persons identified as the
document authors. All rights reserved.
This document is subject to BCP 78 and the IETF Trust's Legal
Provisions Relating to IETF Documents
(https://trustee.ietf.org/license-info) in effect on the date of
publication of this document. Please review these documents
carefully, as they describe your rights and restrictions with respect
to this document. Code Components extracted from this document must
include Simplified BSD License text as described in Section 4.e of
the Trust Legal Provisions and are provided without warranty as
described in the Simplified BSD License.
Table of Contents
1. Introduction . . . . . . . . . . . . . . . . . . . . . . . . 3
1.1. Terminology . . . . . . . . . . . . . . . . . . . . . . . 5
2. Challenges . . . . . . . . . . . . . . . . . . . . . . . . . 6
2.1. No Access to End-to-End Transport Information . . . . . . 6
2.2. Path Asymmetry . . . . . . . . . . . . . . . . . . . . . 6
2.3. Reordering vs. Spurious Retransmission . . . . . . . . . 6
2.4. Informing the End-to-End Transport . . . . . . . . . . . 7
2.5. Congestion Detection . . . . . . . . . . . . . . . . . . 8
3. Simplifying assumptions . . . . . . . . . . . . . . . . . . . 8
4. LOOPS Generic Information Set . . . . . . . . . . . . . . . . 9
4.1. Setup Information . . . . . . . . . . . . . . . . . . . . 9
4.2. Forward Information . . . . . . . . . . . . . . . . . . . 9
4.3. Reverse Information . . . . . . . . . . . . . . . . . . . 10
5. LOOPS General Operation . . . . . . . . . . . . . . . . . . . 11
5.1. Initial Packet Sequence Number . . . . . . . . . . . . . 11
5.2. Acknowledgement Generation . . . . . . . . . . . . . . . 11
5.3. Measurement . . . . . . . . . . . . . . . . . . . . . . . 12
5.4. Loss detection and Recovery . . . . . . . . . . . . . . . 12
5.4.1. Local Retransmission . . . . . . . . . . . . . . . . 12
5.4.2. FEC . . . . . . . . . . . . . . . . . . . . . . . . . 13
5.5. Discussion . . . . . . . . . . . . . . . . . . . . . . . 13
6. Sketches of Bindings to Tunnel Protocols . . . . . . . . . . 13
6.1. Embedding LOOPS in Geneve . . . . . . . . . . . . . . . . 14
6.2. Embedding LOOPS in GUE . . . . . . . . . . . . . . . . . 14
7. IANA Considerations . . . . . . . . . . . . . . . . . . . . . 14
8. Security Considerations . . . . . . . . . . . . . . . . . . . 15
9. Informative References . . . . . . . . . . . . . . . . . . . 15
Appendix A. Protocol used in Prototype Implementation . . . . . 16
A.1. Block Code FEC . . . . . . . . . . . . . . . . . . . . . 17
Appendix B. Transparent mode . . . . . . . . . . . . . . . . . . 18
B.1. Packet identification . . . . . . . . . . . . . . . . . . 19
Welzl & Bormann Expires November 28, 2019 [Page 2]
Internet-Draft LOOPS May 2019
B.2. Generic information and protocol operation . . . . . . . 20
Acknowledgements . . . . . . . . . . . . . . . . . . . . . . . . 20
Authors' Addresses . . . . . . . . . . . . . . . . . . . . . . . 20
1. Introduction
Today's networks exhibit a wide variety of data rates and, relative
to those, processing power and memory capacities of nodes acting as
routers. For instance, networks that employ tunneling to build
overlay networks may position powerful virtual router nodes in the
network to act as tunnel endpoints. The capabilities available in
the more powerful cases provide new opportunities for optimizations.
LOOPS (Local Optimizations on Path Segments) aims to provide local
(not end-to-end but in-network) recovery of lost packets to achieve
better data delivery. [I-D.li-tsvwg-loops-problem-opportunities]
provides an overview over the problems and optimization opportunities
that LOOPS could address. One simplifying assumption (Section 3) in
the present document is that LOOPS segments operate independently
from each other, each as a pair of a LOOPS Ingress and a LOOPS Egress
node.
The present document is a strawman for the set of information that
would be interchanged in a LOOPS protocol between these nodes,
without already defining a specific data packet format. The main
body of the document defines a mode of the LOOPS protocol that is
based on traditional tunneling, the "tunnel mode". Appendix B is an
even rougher strawman of a radically different, alternative mode that
we call "transparent mode". These different modes may be applicable
to different usage scenarios and will be developed in parallel, with
a view of ultimately standardizing one or both of them.
For tunnel mode, the generic information set needs to be mapped to a
specific encapsulation protocol to actually run the LOOPS
optimizations. LOOPS is not tied to any specific overlay protocol,
but is meant to run embedded into a variety of tunnel protocols.
LOOPS information is added as part of a tunnel protocol header at the
LOOPS ingress as shown in Figure 1. The current version of this
document contains sketches of bindings to GUE [I-D.ietf-intarea-gue]
and Geneve [I-D.ietf-nvo3-geneve].
Welzl & Bormann Expires November 28, 2019 [Page 3]
Internet-Draft LOOPS May 2019
+------------------------------------+
| Outer header |
+------------------------------------+
/ | Tunnel Base Header |
/ +------------------------------------+\
Tunnel | +-------------------------+ | \
Header ~ | LOOPS Information | ~ Tunnel Header
\ | +-------------------------+ | Extensions
\ +------------------------------------+ /
| Data packet |
+------------------------------------+
Figure 1: Packet in Tunnel with LOOPS Information
Figure 2 is extracted from the LOOPS problems and opportunities
document [I-D.li-tsvwg-loops-problem-opportunities]. It illustrates
the basic architecture and terms of the applicable scenario of LOOPS.
Not all of the concepts introduced in the problems and opportunities
document are actually used in the current strawman specification;
Section 3 lays out some simplifying assumptions that the present
proposal makes.
ON=overlay node
UN=underlay node
+---------+ +---------+
| App | <---------------- end-to-end ---------------> | App |
+---------+ +---------+
|Transport| <---------------- end-to-end ---------------> |Transport|
+---------+ +---------+
| | | |
| | +--+ path +--+ path segment2 +--+ | |
| | | |<-seg1->| |<--------------> | | | |
| Network | +--+ |ON| +--+ |ON| +--+ +----+ |ON| | Network |
| |--|UN|--| |--|UN|--| |--|UN|---| UN |--| |--| |
+---------+ +--+ +--+ +--+ +--+ +--+ +----+ +--+ +---------+
End Host End Host
<--------------------------------->
LOOPS domain: path segments enabling
optimization for local in-network recovery
Figure 2: LOOPS Usage Scenario
Welzl & Bormann Expires November 28, 2019 [Page 4]
Internet-Draft LOOPS May 2019
1.1. Terminology
This document makes use of the terminology defined in
[I-D.li-tsvwg-loops-problem-opportunities]. This section defines
additional terminology used by this document.
Data packets: The payload packets that enter and exit a LOOPS
segment.
LOOPS Segment: A part of an end-to-end path covered by a single
instance of the LOOPS protocol, the sub-path between the LOOPS
Ingress and the LOOPS Egress.
LOOPS Ingress: The node that forwards data packets and forward
information into the LOOPS segment, potentially performing
retransmission and forward error correction based on
acknowledgements and measurements received from the LOOPS Egress.
LOOPS Egress: The node that receives the data packets and forward
information from the LOOPS ingress, sends acknowledgements and
measurements back to the LOOPS ingress (reverse information),
potentially recovers data packets from forward error correction
information received.
LOOPS Nodes: Collective term for LOOPS Ingress and LOOPS Egress in a
LOOPS Segment.
Forward Information: Information that is added to the stream of data
packets in the forward direction by the LOOPS Ingress.
Reverse Information: Information that flows in the reverse
direction, from the LOOPS Egress back to the LOOPS Ingress.
Setup Information: Information that is not transferred as part of
the Forward or Reverse Information, but is part of the setup of
the LOOPS Nodes.
PSN: Packet Sequence Number, a sequence number identifying a data
packet.
Sender: Original sender of a packet on an end-to-end path that
includes one or more LOOPS segment(s).
Receiver: Ultimate receiver of a packet on an end-to-end path that
includes one or more LOOPS segment(s).
Welzl & Bormann Expires November 28, 2019 [Page 5]
Internet-Draft LOOPS May 2019
2. Challenges
LOOPS has to perform well in the presence of some challenges, which
are discussed in this section.
2.1. No Access to End-to-End Transport Information
LOOPS is defined to be independent of the content of the packets
being forwarded: there is no dependency on transport-layer or higher
information. The intention is to keep LOOPS useful with a traffic
mix that may contain encrypted transport protocols such as QUIC as
well as encrypted VPN traffic.
2.2. Path Asymmetry
A LOOPS segment is defined as a unidirectional forwarding path. The
tunnel might be shared with a LOOPS segment in the inverse direction;
this then allows to piggyback Reverse Information on encapsulated
packets on that segment. But there is no guarantee that the inverse
direction of any end-to-end-path crosses that segment, so the LOOPS
optimizations have to be useful on their own in each direction.
2.3. Reordering vs. Spurious Retransmission
The end-to-end transport layer protocol may have its own
retransmission mechanism to recover lost packets. When LOOPS
recovers a loss, ideally this local recovery would avoid the
triggering of a retransmission at the end-to-end sender.
Whether this is possible depends on the specific end-to-end mechanism
used for triggering retransmission. When end-to-end retransmission
is triggered by receiving a sequence of duplicate acknowledgements
(DUPACKs), and with more than a few packets in flight, the recovered
packet is likely to be too late to fill the hole in the sequence
number space that triggers the DUPACK detection.
(Given a reasonable setting of parameters, the local retransmission
will still arrive earlier than the end-to-end retransmission and will
possibly unblock application processing earlier; with spurious
retransmission detection, there also will be little long-term effect
on the send rate.)
The waste of bandwidth caused by a DUPACK-based end-to-end
retransmission can be avoided when the end-to-end loss detection is
based on time instead of sequence numbers, e.g., with RACK
[I-D.ietf-tcpm-rack]. This requires a limit on the additional
latency that LOOPS will incur in its attempt to recover the loss
locally. In the present version of this document, opportunity to set
Welzl & Bormann Expires November 28, 2019 [Page 6]
Internet-Draft LOOPS May 2019
such a limit is provided in the Setup Information. The limit can be
used to compute a deadline for retransmission, but also can be used
to choose FEC parameters that keep extra latency low.
2.4. Informing the End-to-End Transport
Congestion control at the end-to-end sender is used to adapt its
sending rate to the network congestion status. In typical TCP
senders, packet loss implies congestion and leads to a reduction in
sending rate. With LOOPS operating, packet loss can be masked from
the sender as the loss may have been locally recovered. In this
case, rate reduction may not be invoked at the sender. This is a
desirable performance improvement if the loss was a random loss.
If LOOPS successfully conceals congestion losses from the end-to-end
transport protocol, that might increase the rate to a level that
congests the LOOPS segment, or that causes excessive queueing at the
LOOPS ingress. What LOOPS should be able to achieve is to let the
end host sender invoke the rate reduction mechanism when there is a
congestion loss no matter if the lost packet was recovered locally.
As with any tunneling protocol, information about congestion events
inside the tunnel needs to be exported to the end-to-end path the
tunnel is part of. See e.g., [RFC6040] for a discussion of how to do
this in the presence of ECN. A more recent draft,
[I-D.ietf-tsvwg-tunnel-congestion-feedback], proposes to activate ECN
for the tunnel regardless of whether the end-to-end protocol signals
the use of an ECN-capable transport (ECT), which requires more
complicated action at the tunnel egress.
A sender that interprets reordering as a signal of packet loss
(DUPACKs) initiates a retransmission and reduces the sending rate.
When spurious retransmission detection (e.g., via F-RTO [RFC5862] or
DSACK [RFC3708] is enabled by the TCP sender, it will often be able
undo the unnecessary window reduction. As LOOPS recovers lost
packets locally, in most cases the end host sender will eventually
find out its reordering-based retransmission (if any) is spurious.
This is an appropriate performance improvement if the loss was a
random loss. For congestion losses, a congestion event needs to be
signaled to the end-to-end transport.
If the end-to-end transport is ECN-capable (which is visible at the
IP level), congestion loss events can easily be signaled to them by
setting the CE (congestion experienced) mark. If LOOPS detects a
congestion loss for a non-ECT packet, it needs to signal a congestion
loss event by introducing a packet loss. This can be done by
choosing not to retransmit or repair the packet loss locally in this
case. Note that one congestion loss per end-to-end RTT is sufficient
Welzl & Bormann Expires November 28, 2019 [Page 7]
Internet-Draft LOOPS May 2019
to provide the rate reduction, so LOOPS may still be able to recover
most packets, in particular for burst losses. (As LOOPS does not
interact with the end-to-end transport, it does not know the end-to-
end RTT. Some lower bound derived from configuration and
measurements could be used instead.)
2.5. Congestion Detection
Properly informing the end-to-end transport protocol about congestion
loss events requires distinguishing these from random losses. In
some special cases, distinguishing information may be available from
a link layer (e.g., see Section 3 of
[I-D.li-tsvwg-loops-problem-opportunities]). By enabling ECN inside
the tunnel, congestion events experienced at ECN-capable routers will
usually be identified by the CE mark, which clearly rules out a
random loss.
In the general case, the segment may be composed of hops without such
special indications. In these cases, some detection mechanism is
required to provide this distinguishing information. The specific
mechanism used by an implementation is out of scope of LOOPS, but
LOOPS will need to provide measurement information for this
mechanism. For instance, congestion detection might be based on path
segment latency information, the proper measurement of which
therefore requires special attention in LOOPS.
3. Simplifying assumptions
The above notwithstanding, Implementations may want to make use of
indicators such as transport layer port numbers to partition a tunnel
flow into separate application flows, e.g., for active queue
management (AQM). Any such functionality is orthogonal to the LOOPS
protocol itself and thus out of scope for the present document.
One observation that simplifies the design of LOOPS in comparison to
that of a reliable transport protocol is that LOOPS does not _have_
to recover every packet loss. Therefore, probabilistic approaches,
and simply giving up after some time has elapsed, can simplify the
protocol significantly.
For now, we assume that LOOPS segments that may line up on an end-to-
end path operate independently of each other. Since the objective of
LOOPS ultimately is to assist the end-to-end protocol, it is likely
that some cooperation between them would be beneficial, e.g., to
obtain some measurements that cover a larger part of the end-to-end
path. For instance, cooperating LOOPS segments could try to divide
up permissible increases to end-to-end latency between them. This is
out of scope for the present version.
Welzl & Bormann Expires November 28, 2019 [Page 8]
Internet-Draft LOOPS May 2019
Another simplifying assumption is that LOOPS nodes have reasonably
precise absolute time available to them, so there is no need to
burden the LOOPS protocol with time synchronization. How this is
achieved is out of scope.
LOOPS nodes are created and set up (information about their peers,
parameters) by some control plane mechanism that is out of scope for
this specification. This means there is no need in the LOOPS
protocol itself to manage setup information.
4. LOOPS Generic Information Set
This section sketches a generic information set for the LOOPS
protocol. Entries marked with (*) are items that may not be
necessary and probably should be left out of an initial
specification.
4.1. Setup Information
Setup Information might include:
o encapsulation protocol in use, and its vital parameters
o identity of LOOPS ingress and LOOPS egress; information relevant
for running the encapsulation protocol such as port numbers
o target maximum latency increase caused by the operation of LOOPS
on this segment
o maximum retransmission count (*)
In the data plane, we have forward information (information added to
each data packet) and reverse information. The latter can be sent in
separate packets (e.g., Geneve control-only packets
[I-D.ietf-nvo3-geneve]) and/or piggybacked like the forward
information.
4.2. Forward Information
In the forward information, we have identified:
o tunnel type (a few bits, meaning agreed between Ingress and
Egress)
o packet sequence number PSN (20+ bits), counting the LOOPS packets
transmitted by the LOOPS ingress (i.e., retransmissions receive a
new PSN)
Welzl & Bormann Expires November 28, 2019 [Page 9]
Internet-Draft LOOPS May 2019
o an "ACK desirable" flag (one bit, usually set for a certain
percentage of the data packets only)
o anything that the FEC scheme needs.
The first four together (say, 3+24+4+1) might even fit into 32 bits,
but probably need up to 48 bits total. FEC info of course often
needs more space.
(Note that in this proposal there is no timestamp in the forward
information; see Section 5.3.)
24 bits of PSN, minus one bit for sequence number arithmetic, gives 8
million packets (or 2.4 GB at typical packet sizes) per worst-case
RTT. So if that is, say, 30 seconds, this would be enough to fill
640 Mbit/s.
4.3. Reverse Information
For the reverse information, we have identified:
o one optional block 1, possibly repeated:
o PSN being acknowledged
o absolute time of reception for the packet acknowledged (PSN)
o one optional block 2, possibly repeated:
o an ACK bitmap (based on PSN), always starting at a multiple of 8
o a delta indicating the end PSN of the bitmap (actually the first
PSN that is beyond it), using (Acked-PSN & ~7) + 8*(delta+1) as
the end of the bitmap. Acked-PSN in that formula is the previous
block 1 PSN seen in this packet, or 0 if none so far.
Block 1 and Block 2 can be interspersed and repeated. They can be
piggybacked on a reverse direction data packet or sent separately if
none occurs within some timeout. They will usually be aggregated in
some useful form. Block 1 information sets are only returned for
packets that have "ACK desirable" set. Block 2 information is sent
by the receiver based on some saturation scheme (e.g., at least three
copies for each PSN span over time). Still, it might be possible to
go down to 1 or 2 amortized bytes per forward packet spent for all
this.
The latency calculation is done by the sender, who occasionally sets
"ACK desirable", and notes down the absolute time of transmission for
Welzl & Bormann Expires November 28, 2019 [Page 10]
Internet-Draft LOOPS May 2019
this data packet (the timekeeping can be done quite efficiently as
deltas). Upon reception of a block 1 ACK, it can then subtract that
from the absolute time of reception indicated. This assumes time
synchronization between the nodes is at least as good as the
precision of latency measurement needed, which should be no problem
with IEEE 1588 PTP synchronization (but could be if using NTP-based
synchronization only). A sender can freely garbage collect noted
down transmission time information; doing this too early just means
that the quality of the RTT sampling will reduce.
5. LOOPS General Operation
In the Tunnel Mode described in the main body of this document, LOOPS
information is carried by some tunnel encapsulation.
5.1. Initial Packet Sequence Number
There is no connection establishment procedure in LOOPS. The initial
PSN is assigned unilaterally by the LOOPS Ingress.
Because of the short time that is usually set in the maximum latency
increase, there is little damage from a collision of PSNs with
packets still in flight from previous instances of LOOPS.
Collisions can be minimized by assigning initial PSNs randomly, or
using stable storage. Random assignment is more useful for longer
PSNs, where the likelihood of overlap will be low. The specific way
a LOOPS ingress uses stable storage is a local matter and thus out of
scope. (Implementation note: this can be made to work similar to
secure nonce generation with write attenuation: Say, every 10000
packets, the sender notes down the PSN into stable storage. After a
reboot, it reloads the PSN and adds 10000 in sequence number
arithmetic [RFC1982], plus maybe another 10000 so the sender does not
have to wait for the store operation to succeed before sending more
packets.)
5.2. Acknowledgement Generation
A data packet forwarded by the LOOPS ingress always carries PSN
information. The LOOPS egress uses the largest newly received PSN
with the "ACK desired" bit as the ACK number in the block 1 part of
the acknowledgement. This means that the LOOPS ingress gets to
modulate the number of acknowledgement sent by the LOOPS egress.
However, whenever an out-of-order packet arrives while there still
are "holes" in the PSNs received, the LOOPS receiver should generate
a block 2 acknowledgement immediately that the LOOPS sender can use
as a NACK list.
Welzl & Bormann Expires November 28, 2019 [Page 11]
Internet-Draft LOOPS May 2019
Reverse information can be piggybacked in a reverse direction data
packet. When the reverse direction has no user data to be sent, a
pure reverse information packet needs to be generated. This may be
based on a short delay during which the LOOPS egress waits for a data
packet to piggyback on. (To reduce MTU considerations, the egress
could wait for less-than-full data packets.)
5.3. Measurement
When sending a block 1 acknowledgement, the LOOPS egress indicates
the absolute time of reception of the packet. The LOOPS ingress can
subtract the absolute time of transmission that it still has
available, resulting in one high quality latency sample. (In an
alternative design, the forward information could include the
absolute time of transmission as well, and block1 information would
echo it back. This trades memory management at the ingress for
increased bandwidth and MTU reduction.)
The LOOPS ingress can also use the time of reception of the block 1
acknowledgement to obtain a segment RTT sample. Note that this will
include any wait time the LOOPS egress incurs while waiting for a
piggybacking opportunity -- this is appropriate, as all uses of an
RTT will be for keeping a retransmission timeout.
To maintain quality of information during idle times, the LOOPS
ingress may send keepalive packets, which are discarded at the LOOPS
egress after sending acknowledgements. The indication that a packet
is a keepalive packet is dependent on the encapsulation protocol.
5.4. Loss detection and Recovery
There are two ways for LOOPS local recovery, retransmission and FEC.
5.4.1. Local Retransmission
When retransmission is used as recovery mechanism, the LOOPS ingress
detects a packet loss by receiving a NACK or by local timeout (using
a RTO value that might be calculated as in [RFC6298]). It might
employ a DUPACK-like or a RACK-like mechanism for delayed reaction to
a NACK.
When a retransmission is desired (see Section 2.4 for why it might
not be), the LOOPS ingress performs the local in-network recovery by
retransmitting the packet. Further retransmissions may be desirable
if the NACK is persistent beyond an RTO, as long as the maximum
latency increase is not reached.
Welzl & Bormann Expires November 28, 2019 [Page 12]
Internet-Draft LOOPS May 2019
5.4.2. FEC
FEC is another way to perform local recovery. When FEC is in use, a
FEC header is sent with data packets as well as with special repair
packets added to the flow. The specific FEC scheme used could be
defined in the Setup Information, using a mechanism like [RFC5052].
The FEC rate (amount of redundancy added) and possibly the FEC scheme
could be unilaterally adjusted by the LOOPS ingress in an adaptive
mechanism based on the measurement information.
5.5. Discussion
Without progress in the way that end-host transport protocols handle
reordering, LOOPS will be unable to prevent end-to-end
retransmissions that duplicate effort that is spent in local
retransmissions. It depends on parameters of the path segment
whether this wasted effort is significant or not.
One remedy against this waste could be the introduction of
resequencing at the LOOPS Egress node. This increases overall mean
packet latency, but does not always increase actual end-to-end data
stream latency if a head-of-line blocking transport such as TCP is in
use. For applications with a large percentage of legacy TCP end-
hosts and sufficient processing capabilities at the LOOPS Egress
node, resequencing may be a viable choice. Note that resequencing
could be switched off and on depending on some measurement
information.
To enable resequencing at the LOOPS Egress, a packet numbering scheme
is needed that allows the LOOPS Egress to reconstruct the sequence at
the LOOPS ingress. This could be done by reverting to a traditional
packet sequence number counting incoming data packets, possibly
combined with a "retransmission" bit that indicates that the specific
LOOPS packet is a retransmission and not the original transmission.
(The acknowledgement/measurement ambiguity could be further reduced
by adding transmission counter TC that counts transmission/
retransmission for this PSN; a few bits should be enough for the
limited retransmission envisaged.)
6. Sketches of Bindings to Tunnel Protocols
The LOOPS information defined above in a generic way can be mapped to
specific tunnel encapsulation protocols. Sketches for two tunnel
protocols are given below: Geneve (Section 6.1), and GUE
(Section 6.2).
Welzl & Bormann Expires November 28, 2019 [Page 13]
Internet-Draft LOOPS May 2019
6.1. Embedding LOOPS in Geneve
Geneve [I-D.ietf-nvo3-geneve] is an extensible overlay protocol which
can embed LOOPS functions. Geneve uses TLVs to carry optional
information between NVEs. NVE is logically the same entity as the
LOOPS node.
For Geneve, a new LOOPS TLV needs to be defined and its format needs
to be consistent with LOOPS generic information in Section 4. When
the Geneve LOOPS TLV is put in forward information, NVEs should be
able to process it. Any settings needed can be provided in the Setup
Information.
In the reverse direction, when no data packets are available for
piggybacking, a control only packet will be used to carry the LOOPS
reverse information. Such a control only packet sets the 'O' bit in
the Geneve header and has no real user data.
VNI is a mandatory field in Geneve base header. The LOOPS TLV should
function on the tunnel between two NVEs without looking at the VNI
value. The LOOPS PSN number space is local to the overlay tunnel
regardless of the VNI inside. At the ingress NVE, there are
different ways to decide whether a packet should go to LOOPS enabled
tunnel, e.g. by protocol number (TCP/UDP certain ports) or by VNI.
6.2. Embedding LOOPS in GUE
GUE [I-D.ietf-intarea-gue] is an extensible overlay protocol which
can embed LOOPS functions. GUE uses flags to indicate the presence
of fixed length header extensions. It also allows variable length
extensions to be put in "Private data" field. A new LOOPS data block
in the "private data" field needs to be defined based on the LOOPS
generic information in Section 4.
In the reverse direction, when no data packets are available for
piggybacking, LOOPS reverse information is carried in a control
message with the C-bit set in the GUE header. The Proto/ctype field
contains a control message type when C bit is set. Hence a new
control message type should be defined for such LOOPS reverse
information.
7. IANA Considerations
No IANA action is required at this stage. When a LOOPS
representation is designed for a specific tunneling protocol, new
codepoints will be required in the registries that pertain to that
protocol.
Welzl & Bormann Expires November 28, 2019 [Page 14]
Internet-Draft LOOPS May 2019
8. Security Considerations
To be defined.
9. Informative References
[RFC1982] Elz, R. and R. Bush, "Serial Number Arithmetic", RFC 1982,
DOI 10.17487/RFC1982, August 1996,
<https://www.rfc-editor.org/info/rfc1982>.
[RFC3708] Blanton, E. and M. Allman, "Using TCP Duplicate Selective
Acknowledgement (DSACKs) and Stream Control Transmission
Protocol (SCTP) Duplicate Transmission Sequence Numbers
(TSNs) to Detect Spurious Retransmissions", RFC 3708,
DOI 10.17487/RFC3708, February 2004,
<https://www.rfc-editor.org/info/rfc3708>.
[RFC5052] Watson, M., Luby, M., and L. Vicisano, "Forward Error
Correction (FEC) Building Block", RFC 5052,
DOI 10.17487/RFC5052, August 2007,
<https://www.rfc-editor.org/info/rfc5052>.
[RFC5862] Yasukawa, S. and A. Farrel, "Path Computation Clients
(PCC) - Path Computation Element (PCE) Requirements for
Point-to-Multipoint MPLS-TE", RFC 5862,
DOI 10.17487/RFC5862, June 2010,
<https://www.rfc-editor.org/info/rfc5862>.
[RFC6040] Briscoe, B., "Tunnelling of Explicit Congestion
Notification", RFC 6040, DOI 10.17487/RFC6040, November
2010, <https://www.rfc-editor.org/info/rfc6040>.
[RFC6298] Paxson, V., Allman, M., Chu, J., and M. Sargent,
"Computing TCP's Retransmission Timer", RFC 6298,
DOI 10.17487/RFC6298, June 2011,
<https://www.rfc-editor.org/info/rfc6298>.
[RFC6330] Luby, M., Shokrollahi, A., Watson, M., Stockhammer, T.,
and L. Minder, "RaptorQ Forward Error Correction Scheme
for Object Delivery", RFC 6330, DOI 10.17487/RFC6330,
August 2011, <https://www.rfc-editor.org/info/rfc6330>.
[I-D.ietf-tcpm-rack]
Cheng, Y., Cardwell, N., Dukkipati, N., and P. Jha, "RACK:
a time-based fast loss detection algorithm for TCP",
draft-ietf-tcpm-rack-05 (work in progress), April 2019.
Welzl & Bormann Expires November 28, 2019 [Page 15]
Internet-Draft LOOPS May 2019
[I-D.ietf-nvo3-geneve]
Gross, J., Ganga, I., and T. Sridhar, "Geneve: Generic
Network Virtualization Encapsulation", draft-ietf-
nvo3-geneve-13 (work in progress), March 2019.
[I-D.ietf-intarea-gue]
Herbert, T., Yong, L., and O. Zia, "Generic UDP
Encapsulation", draft-ietf-intarea-gue-07 (work in
progress), March 2019.
[I-D.li-tsvwg-loops-problem-opportunities]
Yizhou, L. and X. Zhou, "LOOPS (Localized Optimizations of
Path Segments) Problem Statement and Opportunities",
draft-li-tsvwg-loops-problem-opportunities-02 (work in
progress), May 2019.
[I-D.ietf-tsvwg-tunnel-congestion-feedback]
Wei, X., Yizhou, L., Boutros, S., and L. Geng, "Tunnel
Congestion Feedback", draft-ietf-tsvwg-tunnel-congestion-
feedback-07 (work in progress), May 2019.
Appendix A. Protocol used in Prototype Implementation
This appendix describes, in a somewhat abstracted form, the protocol
as used in a prototype implementation, as described by Yizhou Li, and
Xingwang Zhou.
The prototype protocol can be run in one of two modes (defined by
preconfiguration):
o Retransmission mode
o Forward Error Correction (FEC) mode
Forward information is piggybacked in data packets.
Reverse information can be carried in a pure acknowledgement packet
or piggybacked when carrying packets for the inverse direction.
The forward information includes:
o Packet Sequence Number (PSN) (32 bits): This identifies a packet
over a specific overlay segment from a specific LOOPS Ingress. If
a packet is retransmitted by LOOPS, the retransmission uses the
original PSN.
o Timestamp (32 bits): Information, in a format local to the LOOPS
ingress, that provides the time when the packet was sent. In the
Welzl & Bormann Expires November 28, 2019 [Page 16]
Internet-Draft LOOPS May 2019
current implementation, a 32-bit unsigned value specifying the
time delta in some granularity from the epoch time to the sending
time of the packet carrying this timestamp. The granularity can
be from 1 ms to 1 second. The epoch time follows the current TCP
practice which is 1 January 1970 00:00:00 UTC. Note that a
retransmitted packet uses its own Timestamp.
o FEC Info for Block Code (56 bits): This header is used in FEC
mode. It currently only provides for a block code FEC scheme. It
includes the Source Block Number (SBN), Encoding Symbol ID (ESI),
number of symbols in a single source block and symbol size.
Appendix A.1 gives more details on FEC.
The reverse information includes:
o ACK Number (32 bits): The largest (in sequence number arithmetic
[RFC1982]) PSN received so far.
o NACK List (variable): This indicates an array of PSN numbers to
describe the PSN "holes" preceding the ACK number. It
conceptually lists the PSNs of every packet perceived as lost by
the LOOPS egress. In actual use, it is truncated.
o Echoed Timestamp (32 bits): The timestamp received with the packet
being acknowledged.
A.1. Block Code FEC
The prototype currently uses a block code FEC scheme (RaptorQ
[RFC6330]). The fields in the FEC Info forward information are:
o Source Block Number (SBN): 16 bits. An integer identifier for the
source block that the encoding symbols within the packet relate
to.
o Encoding Symbol ID (ESI): 16 bits. An integer identifier for the
encoding symbols within the packet.
o K: 8 bits. Number of symbols in a single source block.
o T: 16 bits. Symbol size in bytes.
The LOOPS Ingress uses the data packet in Figure 1 to generate the
encoding packet. Both source packets and repair packets carry the
FEC header information; the LOOPS Egress reconstructs the data
packets from both kinds of packets. The LOOPS Egress currently
resequences the forwarded and reconstructed packets, so they are
Welzl & Bormann Expires November 28, 2019 [Page 17]
Internet-Draft LOOPS May 2019
passed on in-order when the lost packets are recoverable within the
source block.
The LOOPS Nodes need to agree on the use of FEC block mode and on the
specific FEC Encoding ID to use; this is currently done by
configuration.
Appendix B. Transparent mode
This appendix defines a very different way to provide the LOOPS
services, "transparent mode". (We call the protocol described in the
main body of the document "encapsulated mode".)
In transparent mode, the idea is that LOOPS does not meddle with the
forward transmission of data packets, but runs on the side exchanging
additional information.
An implementation could be based on conventional forwarding switches
that just provide a copy of the ingress and egress packet stream to
the LOOPS implementations. The LOOPS process would occasionally
inject recovered packets back into the LOOPS egress node's forwarding
switch, see Figure 3.
Welzl & Bormann Expires November 28, 2019 [Page 18]
Internet-Draft LOOPS May 2019
|
+-------+-------------------------------------------+
| | |
| +----+--------+ +-------------------+ |
| | | copy | | | |
| | |----------------> LOOPS ingress | |
| | | | | | ^ | |
| +----+--------+ +-----|-----|-------+ |
| data|packets forward| |reverse |
| | info| |info |
+-------+------------------|-----|------------------+
| | |
+-------+------------------|-----|------------------+
| | | | |
| +----+---------+ +----|-----|----------+ |
| | | copy | | v | | |
| | |---------|---|---> LOOPS egress | |
| | | | | | |
| | |<--------|---|---- inject | |
| +----+---------+ +---------------------+ |
| | |
+-------+-------------------------------------------+
|
v
Figure 3: LOOPS Transparent Mode
The obvious advantage of transparent mode is that no encapsulation is
needed, reducing processing requirements and keeping the MTU
unchanged. The obvious disadvantage is that no forward information
can be provided with each data packet, so a replacement needs to be
found for the PSN (packet sequence number) employed in encapsulated
mode. Any forward information beyond the data packets is sent in
separate packets exchanged directly between the LOOPS nodes.
B.1. Packet identification
Retransmission mode and FEC mode differ in their needs for packet
identification. For retransmission mode, a somewhat probabilistic
accuracy of the packet identification is sufficient, for FEC mode,
packet identification should not make mistakes (as these would lead
to faultily reconstructed packets).
In Retransmission mode, misidentification of a packet could lead to
measurement errors as well as missed retransmission opportunities.
The latter will be fixed end-to-end. The tolerance for measurement
errors would influence the degree of accuracy that is aimed for.
Welzl & Bormann Expires November 28, 2019 [Page 19]
Internet-Draft LOOPS May 2019
Packet identification can be based on a cryptographic hash of the
packet, computed in LOOPS ingress and egress using the same algorithm
(excluding fields that can change in transit, such as TTL/hop limit).
The hash can directly be used as a packet number, or it can be sent
in the forward information together with a packet sequence number,
establishing a mapping.
For probabilistic packet identification, it is almost always
sufficient to hash the first few (say, 64) bytes of the packet; all
known transport protocols keep sufficient identifying information in
that part (and, for encrypted protocols, the entropy will be
sufficient). Any collisions of the hash could be used to disqualify
the packet for measurement purposes, minimizing the measurement
errors; this could allow rather short packet identifiers in
retransmission mode.
For FEC mode, the packet identification together with the per-packet
FEC information needs to be sent in the (separate) forward
information, so that a systematic code can be reconstructed. For
retransmission mode, there is no need to send any forward information
for most packets, or a mapping from packet identifiers to packet
sequence numbers could be sent in the forward information (probably
in some aggregated form). The latter would allow keeping the
acknowledgement form described in the main body (with aggregate
acknowledgement); otherwise, packet identifiers need to be
acknowledged. With this change, the LOOPS egress will send reverse
information as in the encapsulating LOOPS protocol.
B.2. Generic information and protocol operation
With the changes outlined above, transparent mode operates just as
encapsulated mode. If packet sequence numbers are not used, there is
no use for block2 reverse information; if they are used, a new block3
needs to be defined that provides the mapping from packet identifiers
to packet sequence numbers in the forward information. To avoid MTU
reduction, some mechanism will be needed to encapsulate the actual
FEC information (additional packets) in the forward information.
Acknowledgements
Sami Boutros helped with sketching the use of Geneve (Section 6.1),
and Tom Herbert helped with sketching the use of GUE (Section 6.2).
Authors' Addresses
Welzl & Bormann Expires November 28, 2019 [Page 20]
Internet-Draft LOOPS May 2019
Michael Welzl
University of Oslo
PO Box 1080 Blindern
Oslo N-0316
Norway
Phone: +47 22 85 24 20
Email: michawe@ifi.uio.no
Carsten Bormann (editor)
Universitaet Bremen TZI
Postfach 330440
Bremen D-28359
Germany
Phone: +49-421-218-63921
Email: cabo@tzi.org
Welzl & Bormann Expires November 28, 2019 [Page 21]